© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 118023
    Prev
    Next
    INDEX
    Explanations

    references to popular films and television shows

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Doyle
    -0.06
    usercontent
    -0.06
    chwitz
    -0.06
    yt
    -0.06
    _intr
    -0.06
    ury
    -0.06
     Albums
    -0.06
     UFO
    -0.06
    570
    -0.06
    otto
    -0.06
    POSITIVE LOGITS
     movie
    0.10
    movie
    0.09
     film
    0.07
    -themed
    0.07
    Exited
    0.07
    ä½ľèĢħ
    0.07
     Movie
    0.07
    -era
    0.07
     cast
    0.07
    /copyleft
    0.07
    Activations Density 0.063%

    No Known Activations